Yes bridging the gap between symbolic and subsymbolic representations is one of the important goals of the project.
On Wednesday, February 22, 2017 at 2:40:53 AM UTC+1, Gaurav Gautam wrote: > > Very interesting. I understand that opencog has diverse applications but > what I wanted to ask was if going from subsymbolic to symbolic > representation is one of the central goals. I am not an expert but it > seemed to me that doing this is the key to general intelligence. Am I wrong > when I say that? > > On Wednesday, February 22, 2017 at 2:27:02 AM UTC+5:30, Alex wrote: >> >> There is boom of neural network translation. Maybe it is possible to >> extract formal grammars, symbolic NLP processors from the neural networks >> that are trained for translation... >> > -- You received this message because you are subscribed to the Google Groups "opencog" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To post to this group, send email to [email protected]. Visit this group at https://groups.google.com/group/opencog. To view this discussion on the web visit https://groups.google.com/d/msgid/opencog/362c88b9-e6c5-4828-b8c7-8e3d42e734ae%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
